© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5478
    Prev
    Next
    INDEX
    Explanations

    references to actions or procedures linked to data retrieval or file handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.85
    webElementXpaths
    -0.82
    parsedMessage
    -0.80
     queſta
    -0.79
    تقاوى
    -0.79
     Italijani
    -0.78
     betweenstory
    -0.78
    <unused68>
    -0.77
    queryInterface
    -0.77
    <unused28>
    -0.77
    POSITIVE LOGITS
    <strong>
    0.44
    <eos>
    0.40
     
    0.38
    <b>
    0.36
    <u>
    0.35
    【
    0.35
                 
    0.34
           
    0.34
     ❤️
    0.33
             
    0.33
    Activations Density 0.561%

    No Known Activations